© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1973
    Prev
    Next
    INDEX
    Explanations

    contextual understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ء
    2.07
    crypt
    1.80
     bere
    1.80
    års
    1.80
    ാപാ
    1.79
    uct
    1.79
     الابتدائي
    1.78
    anmoins
    1.74
    mich
    1.73
    anoi
    1.72
    POSITIVE LOGITS
     打开
    2.08
     布
    2.00
     性
    1.96
    לע
    1.92
    CopyWith
    1.91
     천
    1.88
     花
    1.85
    즈
    1.84
    üğünüz
    1.84
    道德
    1.84
    Activations Density 0.259%

    No Known Activations